Zelta MCP Server

Zelta MCP Server

Enables connecting to Zelta through the Model Context Protocol for use with Claude Desktop, Cursor, or Continue.dev.

Category
Visit Server

README

@finaegis/mcp

Connect Claude Desktop, Cursor, or Continue.dev to Zelta via the Model Context Protocol.

First-time login

npx -y @finaegis/mcp --login

This prints an authorization URL to the terminal and (where possible) opens it in your browser. After you complete consent, the token is persisted and the wrapper exits. You can re-run --login at any time to refresh credentials.

Configure (Claude Desktop)

Once logged in, add to claude_desktop_config.json:

{
  "mcpServers": {
    "zelta": { "command": "npx", "args": ["-y", "@finaegis/mcp"] }
  }
}

Token storage

By default, tokens are stored in $XDG_CONFIG_HOME/finaegis-mcp/tokens.json (typically ~/.config/finaegis-mcp/tokens.json) with file permissions 0600 (read/write for the owning user only). The file is plain JSON, not encrypted at rest.

Optional: OS keychain backend. If you prefer macOS Keychain / Windows Credential Manager / Linux libsecret, install keytar globally and opt in:

npm i -g keytar
FINAEGIS_MCP_TOKEN_STORE=keychain npx -y @finaegis/mcp --login

keytar is not a dependency of this package — it's a native module that fails to install on common environments (WSL2, Docker, Alpine, CI). Keeping the default install pure JavaScript means npx -y @finaegis/mcp just works everywhere.

Environment overrides

Variable Default
MCP_SERVER_URL https://mcp.zelta.app/mcp
MCP_AUTH_SERVER https://zelta.app
MCP_OAUTH_NO_BROWSER unset — set to 1 to print the auth URL instead of opening a browser
FINAEGIS_MCP_TOKEN_STORE file (default) — set to keychain to use the OS keychain via keytar (must be installed separately)

Troubleshooting

  • Browser does not open — set MCP_OAUTH_NO_BROWSER=1 and follow the URL printed to stderr.
  • Token expired — log out and re-auth: npx @finaegis/mcp --logout.
  • libsecret-1.so.0: cannot open shared object file — only happens if you opted into FINAEGIS_MCP_TOKEN_STORE=keychain on a Linux system without libsecret. Unset the variable (the default file store needs no native deps) or install libsecret-1-dev + a keyring daemon.

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured